Tissue classification for laparoscopic image understanding based on multispectral texture analysis.

File Description SizeFormat 
Submitted manuscript unmarked changes.pdfAccepted version1.55 MBAdobe PDFView/Open
Title: Tissue classification for laparoscopic image understanding based on multispectral texture analysis.
Authors: Zhang, Y
Wirkert, SJ
Iszatt, J
Kenngott, H
Wagner, M
Mayer, B
Stock, C
Clancy, NT
Elson, DS
Maier-Hein, L
Item Type: Journal Article
Abstract: Intraoperative tissue classification is one of the prerequisites for providing context-aware visualization in computer-assisted minimally invasive surgeries. As many anatomical structures are difficult to differentiate in conventional RGB medical images, we propose a classification method based on multispectral image patches. In a comprehensive ex vivo study through statistical analysis, we show that (1) multispectral imaging data are superior to RGB data for organ tissue classification when used in conjunction with widely applied feature descriptors and (2) combining the tissue texture with the reflectance spectrum improves the classification performance. The classifier reaches an accuracy of 98.4% on our dataset. Multispectral tissue analysis could thus evolve as a key enabling technique in computer-assisted laparoscopy.
Issue Date: 25-Jan-2017
Date of Acceptance: 16-Dec-2016
URI: http://hdl.handle.net/10044/1/45836
DOI: https://dx.doi.org/10.1117/1.JMI.4.1.015001
ISSN: 2329-4310
Publisher: Society of Photo-optical Instrumentation Engineers (SPIE)
Journal / Book Title: Journal of Medical Imaging
Volume: 4
Issue: 1
Copyright Statement: © 2017 Society of Photo-Optical Instrumentation Engineers. One print or electronic copy may be made for personal use only. Systematic reproduction and distribution, duplication of any material in this paper for a fee or for commercial purposes, or modification of the content of the paper are prohibited.
Sponsor/Funder: Commission of the European Communities
Deutsche Forschungsgemeinschaft ( German Research Foundation
Funder's Grant Number: 242991
637960
Keywords: multispectral laparoscopy
multispectral texture analysis
tissue classification
Publication Status: Published
Conference Place: United States
Article Number: 015001
Appears in Collections:Division of Surgery
Faculty of Medicine



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons